Extrapolation Ability of Denoising Diffusion Probabilistic Models for High-Frequency Inductor Core Loss Predictions With DC Bias
Authors:
Open Access
- 10 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 194304-194313
Abstract
Accurate prediction of high-frequency magnetic core losses under DC bias conditions remains a critical challenge in power electronics design. Conventional models, such as empirical curve-fitting approaches and neural networks, often struggle with extrapolation beyond training data, particularly under varying DC bias levels. This paper proposes a Denoising Diffusion Probabilistic Model (DDPM) to enhance the extrapolation capability for core loss predictions in ferrite materials, N87 and 3C90, under DC bias. The proposed DDPM leverages a two-phase noise injection and denoising process to improve prediction stability and generalization. Experimental validation demonstrates that the proposed model achieves an R2 score of 0.9999 for interpolation and maintains high accuracy (R2 = 0.9996)in extrapolation tasks, significantly outperforming conventional CNN (R2 = 0.1856) and GANET (R2 = 0.7974) models. Additionally, the DDPM model enables high-fidelity data augmentation, generating realistic core loss datasets for unseen DC bias conditions. These results highlight the DDPM’s potential as a robust tool for magnetic component design, offering improved accuracy and reliability in both interpolation and extrapolation scenarios.Keywords
Funding Information
- Research on Fault Location and Early Defect Warning Technology (HXKT2025-29-01)
This publication has 25 references indexed in Scilit:
- MagNet Challenge for Data-Driven Power Magnetics ModelingIEEE Open Journal of Power Electronics, 2024
- A Data-Driven Model for Power Loss Estimation of Magnetic Materials Based on Multi-Objective Optimization and Transfer LearningIEEE Open Journal of Power Electronics, 2024
- Artificial Neural Network Aided Loss Maps for Inductors and TransformersIEEE Open Journal of Power Electronics, 2022
- Knowledge-aware Artificial Neural Network for Loss Modeling of Planar Magnetic Components2022
- Convolutional Neural Network (CNN) based Planar Inductor Evaluation and Optimization2022
- Transfer Learning Methods for Magnetic Core Loss Modeling2021
- A Study of Flux Distribution and Impedance in Solid and Laminar Ferrite Cores2019
- On size and magnetics: Why small efficient power inductors are rare2016
- Core losses under DC bias condition based on Steinmetz parameters2010
- Accurate prediction of ferrite core loss with nonsinusoidal waveforms using only Steinmetz parameters2003